Variational framework for partially-measured physical system control:
examples of vision neuroscience and optical random media
- URL: http://arxiv.org/abs/2110.13228v1
- Date: Mon, 25 Oct 2021 19:25:42 GMT
- Title: Variational framework for partially-measured physical system control:
examples of vision neuroscience and optical random media
- Authors: Babak Rahmani, Demetri Psaltis and Christophe Moser
- Abstract summary: We propose a learning procedure to obtain a desired target output from a physical system.
We use Variational Auto-Encoders (VAE) to provide a generative model of the system function.
We showcase the applicability of our method for two datasets in optical physics and neuroscience.
- Score: 0.294656234307089
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: To characterize a physical system to behave as desired, either its underlying
governing rules must be known a priori or the system itself be accurately
measured. The complexity of full measurements of the system scales with its
size. When exposed to real-world conditions, such as perturbations or
time-varying settings, the system calibrated for a fixed working condition
might require non-trivial re-calibration, a process that could be prohibitively
expensive, inefficient and impractical for real-world use cases. In this work,
we propose a learning procedure to obtain a desired target output from a
physical system. We use Variational Auto-Encoders (VAE) to provide a generative
model of the system function and use this model to obtain the required input of
the system that produces the target output. We showcase the applicability of
our method for two datasets in optical physics and neuroscience.
Related papers
- Neural Lumped Parameter Differential Equations with Application in
Friction-Stir Processing [2.158307833088858]
Lumped parameter methods aim to simplify the evolution of spatially-extended or continuous physical systems.
We build upon the notion of the Universal Differential Equation to construct data-driven models for reducing dynamics to that of a lumped parameter.
arXiv Detail & Related papers (2023-04-18T15:11:27Z) - Compensating for non-linear distortions in controlled quantum systems [0.0]
Distortion of the input fields in an experimental platform alters the model accuracy and disturbs the predicted dynamics.
We present an effective method for estimating these distortions which is suitable for non-linear transfer functions of arbitrary lengths and magnitudes.
We have successfully tested our approach for a numerical example of a single Rydberg atom system.
arXiv Detail & Related papers (2022-10-14T14:02:39Z) - Capturing Actionable Dynamics with Structured Latent Ordinary
Differential Equations [68.62843292346813]
We propose a structured latent ODE model that captures system input variations within its latent representation.
Building on a static variable specification, our model learns factors of variation for each input to the system, thus separating the effects of the system inputs in the latent space.
arXiv Detail & Related papers (2022-02-25T20:00:56Z) - Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
We consider the impact of the training set and its structure on the quality of the long-term prediction.
We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
arXiv Detail & Related papers (2021-12-15T20:09:20Z) - Structure-Preserving Learning Using Gaussian Processes and Variational
Integrators [62.31425348954686]
We propose the combination of a variational integrator for the nominal dynamics of a mechanical system and learning residual dynamics with Gaussian process regression.
We extend our approach to systems with known kinematic constraints and provide formal bounds on the prediction uncertainty.
arXiv Detail & Related papers (2021-12-10T11:09:29Z) - Using scientific machine learning for experimental bifurcation analysis
of dynamic systems [2.204918347869259]
This study focuses on training universal differential equation (UDE) models for physical nonlinear dynamical systems with limit cycles.
We consider examples where training data is generated by numerical simulations, whereas we also employ the proposed modelling concept to physical experiments.
We use both neural networks and Gaussian processes as universal approximators alongside the mechanistic models to give a critical assessment of the accuracy and robustness of the UDE modelling approach.
arXiv Detail & Related papers (2021-10-22T15:43:03Z) - Supervised DKRC with Images for Offline System Identification [77.34726150561087]
Modern dynamical systems are becoming increasingly non-linear and complex.
There is a need for a framework to model these systems in a compact and comprehensive representation for prediction and control.
Our approach learns these basis functions using a supervised learning approach.
arXiv Detail & Related papers (2021-09-06T04:39:06Z) - Physics-integrated hybrid framework for model form error identification
in nonlinear dynamical systems [0.0]
For real-life nonlinear systems, the exact form of nonlinearity is often not known and the known governing equations are often based on certain assumptions and approximations.
We propose a novel gray-box modeling approach that not only identifies the model-form error but also utilizes it to improve the predictive capability of the known but approximate governing equation.
arXiv Detail & Related papers (2021-09-01T16:29:21Z) - Controlling nonlinear dynamical systems into arbitrary states using
machine learning [77.34726150561087]
We propose a novel and fully data driven control scheme which relies on machine learning (ML)
Exploiting recently developed ML-based prediction capabilities of complex systems, we demonstrate that nonlinear systems can be forced to stay in arbitrary dynamical target states coming from any initial state.
Having this highly flexible control scheme with little demands on the amount of required data on hand, we briefly discuss possible applications that range from engineering to medicine.
arXiv Detail & Related papers (2021-02-23T16:58:26Z) - Using Data Assimilation to Train a Hybrid Forecast System that Combines
Machine-Learning and Knowledge-Based Components [52.77024349608834]
We consider the problem of data-assisted forecasting of chaotic dynamical systems when the available data is noisy partial measurements.
We show that by using partial measurements of the state of the dynamical system, we can train a machine learning model to improve predictions made by an imperfect knowledge-based model.
arXiv Detail & Related papers (2021-02-15T19:56:48Z) - Modeling System Dynamics with Physics-Informed Neural Networks Based on
Lagrangian Mechanics [3.214927790437842]
Two main modeling approaches often fail to meet requirements: first principles methods suffer from high bias, whereas data-driven modeling tends to have high variance.
We present physics-informed neural ordinary differential equations (PINODE), a hybrid model that combines the two modeling techniques to overcome the aforementioned problems.
Our findings are of interest for model-based control and system identification of mechanical systems.
arXiv Detail & Related papers (2020-05-29T15:10:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.